Best Practices for Federally Compliant Machine Learning Underwriting

The financial services industry is increasingly adopting machine learning (ML) for a range of applications as ML models can consider more data than traditional models.

With the increased use of ML for credit underwriting comes questions about how these models fit within federal regulatory guidance.

We couldn’t agree more about the fundamental need to “explain and defend” complicated ML models. It’s important to understand and monitor underwriting and pricing models to identify potential disparate impact and other fair lending issues.

Our ZAML software quickly renders the inner workings of ML models transparent from creation through deployment.

In this eBook, we cover:

• An overview of ML in model risk management
• ML model development, implementation, and use
• Model validation and monitoring standards
• How ML models fit into governance, policies, and controls